Precision treatment of agricultural objects on a moving platform

Abstract

Various embodiments relate generally to computer vision and automation to autonomously identify and deliver for application a treatment to an object among other objects, data science and data analysis, including machine learning, deep learning, and other disciplines of computer-based artificial intelligence to facilitate identification and treatment of objects, and robotics and mobility technologies to navigate a delivery system, more specifically, to an agricultural delivery system configured to identify and apply, for example, an agricultural treatment to an identified agricultural object. In some examples, a method may include, receiving data representing a policy specifying a type of action for an agricultural object, selecting an emitter with which to perform a type of action for the agricultural object as one of one or more classified subsets, and configuring the agricultural projectile delivery system to activate an emitter to propel an agricultural projectile to intercept the agricultural object.

What is claimed: 
     
       1. A method of operating within a geographic boundary comprising:
 accessing data representing one or more subsets of agricultural objects of an agricultural projectile delivery system; 
 accessing data representing one or more policies, at least one policy associated with a type of action for an agricultural object; 
 identifying, via one or more sensors, one or more agricultural objects of a first classified subset; 
 determining a position of one or more emitters within the geographic boundary, 
 selecting a first emitter of the one or more emitters to perform the type of action for the agricultural object as one of the first classified subset including emitting an agricultural projectile as the first emitter traverses one or more paths within the geographic boundary; and 
 configuring the agricultural projectile delivery system to activate the first emitter to propel the agricultural projectile to intercept the agricultural object. 
 
     
     
       2. The method of  claim 1 , further comprising:
 identifying via the one or more sensors one or more other agricultural objects of a second classified subset, wherein the one or more agricultural objects of the first classified subset are different than one or more other agricultural objects of the second classified subset. 
 
     
     
       3. The method of  claim 2 , further comprising:
 selecting another emitter with which to perform another type of action for another agricultural object as one of the second classified subset, wherein the type of action is different than the another type of action. 
 
     
     
       4. The method of  claim 1 , further comprising:
 associating the first classified subset with a path that includes the position. 
 
     
     
       5. The method of  claim 1 , further comprising:
 predicting spatial locations of the one or more agricultural objects of the first classified subset relative to the position of the one or more emitters. 
 
     
     
       6. The method of  claim 1 , further comprising:
 accessing map data to facilitate autonomous mobility of the agricultural projectile delivery system to traverse the one or more paths. 
 
     
     
       7. The method of  claim 1 , further comprising:
 accessing map data to determine a local position of the agricultural projectile delivery system relative to the identified one or more agricultural objects. 
 
     
     
       8. The method of  claim 7 , wherein the map data includes a map data repository having a plurality of indexed static objects, dynamic objects, agricultural objects, or a combination thereof representing the geographic boundary, the map data acquired previously by the agricultural projectile delivery system. 
     
     
       9. The method of  claim 8 , wherein each of the indexed static objects, dynamic objects, and agricultural objects include one or more captured images or portions of images depicting the indexed static objects, dynamic objects, agricultural objects, or a combination thereof, a timestamp associated with a time of image capture of the one or more captured images, a geo location associated with the indexed static objects, dynamic objects, agricultural objects, or a combination thereof, or a combination thereof. 
     
     
       10. The method of  claim 9 , wherein at least one of the identified one or more agricultural objects is time-series linked to at least one of the indexed agricultural objects. 
     
     
       11. The method of  claim 10 , further comprising:
 generating a time series model of at least one of the identified one or more agricultural objects of the first classified subset based at least in part on the time-series link. 
 
     
     
       12. The method of  claim 7 , wherein the map data is a local map generated in real time via the one or more sensors and one or more processing units configured to detect and identify a location of a static object, dynamic object, or a combination thereof relative to a component of the agricultural projectile delivery system including the one or more emitters. 
     
     
       13. The method of  claim 12 , wherein the position is determined at least in part by the local map data. 
     
     
       14. The method of  claim 1 , wherein identifying the one or more agricultural objects of the first classified subset further comprises:
 identifying via the one or more sensors one or more other agricultural objects of a second classified subset; 
 and 
 activating at least the first emitter to propel agricultural projectiles to intercept each of the one or more agricultural objects of the first classified subset and each of the one or more other agricultural objects of the second classified subset as the agricultural projectile delivery system traverses the one or more paths. 
 
     
     
       15. The method of  claim 1 , wherein identifying the one or more agricultural objects of the first classified subset comprises:
 identifying a type of agricultural object; and 
 selecting the type of action based on a policy for the type of agricultural object. 
 
     
     
       16. The method of  claim 15 , wherein selecting the type of action based on the policy for the type of agricultural object comprises:
 selecting the policy as a function of context. 
 
     
     
       17. The method of  claim 16 , wherein the context includes a stage of growth of the identified one or more agricultural objects. 
     
     
       18. The method of  claim 1 , wherein identifying the one or more agricultural objects of the first classified subset comprises:
 identifying a type of agricultural object as being classified as a blossom. 
 
     
     
       19. The method of  claim 18 , wherein selecting the first emitter to perform the type of action comprises:
 performing one or more of a first type of action to pollinate a king blossom and a second type of action to terminate a lateral blossom as one or more agricultural projectiles. 
 
     
     
       20. The method of  claim 1 , wherein identifying the one or more agricultural objects of the first classified subset comprises:
 identifying a type of agricultural object as being classified as a weed. 
 
     
     
       21. The method of  claim 1 , wherein identifying the one or more agricultural objects of the first classified subset comprises:
 identifying a type of agricultural object as being classified as a portion of soil, a portion of a leaf of a plant, or a portion of a root portion of a plant. 
 
     
     
       22. The method of  claim 21 , wherein selecting the first emitter to perform the type of action comprises:
 performing one or more of a first type of action to apply a portion of fertilizer.